Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    events that are closed or restricted by authorities

    oai_token-act-pair · gpt-3.5-turbo

    references to disciplinary actions or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sonian
    -0.92
    ourke
    -0.84
    Craft
    -0.79
    reprene
    -0.76
    quart
    -0.74
    swick
    -0.70
    CRE
    -0.69
     Aires
    -0.68
    mingham
    -0.67
    venture
    -0.66
    POSITIVE LOGITS
     imposed
    0.83
     penalties
    0.82
     penal
    0.82
    arantine
    0.80
    uation
    0.80
     penalty
    0.75
     checkpoints
    0.75
     banned
    0.73
     prohibited
    0.73
     restrictions
    0.72
    Act Density 0.473%

    No Known Activations